Intelligent workflow event prediction and contingency planning

Abstract

Computer implemented methods, systems, and computer program products include program code executing on a processor(s) generates scenarios based on cognitively analyzing external events. The processor(s) cognitively analyze the process and segmenting the process into components, and for each component: determine an endpoint for each component; determine the scenarios relevant to the component; adjust the endpoint of the component based on the scenarios relevant to the component; applying reinforcement learning to the scenarios relevant to the component to validate impacts of the scenarios on the endpoint and to select a most likely scenario; and implement process changes to terminate the component at the adjusted endpoint.

What is claimed is: 
     
         1 . A computer-implemented method for revising process endpoints by updating strategies based on predicting impacts of exogenous events on original endpoints, comprising:
 generating, by one or more processors, scenarios based on cognitively analyzing external events;   cognitively analyzing, by the one or more processors, the process and segmenting the process into components, for each component:
 determining an endpoint for each component; 
 determining, by the one or more processors, the scenarios relevant to the component; 
 adjusting, by the one or more processors, the endpoint of the component based on the scenarios relevant to the component; 
 applying, by the one or more processors, reinforcement learning to the scenarios relevant to the component to validate impacts of the scenarios on the endpoint and to select a most likely scenario; and 
 implementing, by the one or more processors, process changes to terminate the component at the adjusted endpoint. 
   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the components comprise software and hardware engaged in an aspect of the process. 
     
     
         3 . The computer-implemented method of  claim 2 , wherein the components comprise components of an enterprise computing system. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein cognitively analyzing the process and segmenting the process into the components comprises applying component business model methodology. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein generating the scenarios based on cognitively analyzing external events comprises utilizing a large language model to detect trends in the external events and generating the scenarios based on the detected trends. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein determining the scenarios relevant to the component comprises applying chain of reasoning factoring to the generated scenarios to determine which of the determined scenarios have greater probabilities of impacting the endpoint. 
     
     
         7 . The computer-implemented method of  claim 6 , wherein the scenarios relevant to the component comprise scenarios above a pre-determined probability. 
     
     
         8 . The computer-implemented method of  claim 1 , wherein applying the reinforcement learning comprises:
 generating, by the one or more processors, visuals in a user interface of the scenarios relevant to the component; and   obtaining, by the one or more processors, inputs from a user based on the visuals.   
     
     
         9 . The computer-implemented method of  claim 1 , wherein applying the reinforcement learning to the scenarios relevant to the component to validate the impacts of the scenarios comprises:
 soliciting, by the one or more processors, via a user interface, input from a user, where the input validates the impacts.   
     
     
         10 . The computer-implemented method of  claim 9 , wherein selecting the most likely scenario comprises:
 based on the input from the user, ranking, by the one or more processors, the scenarios relevant to the component; and   selecting, by the one or more processors, the highest ranked scenario.   
     
     
         11 . The computer-implemented method of  claim 8 , wherein generating the visuals comprises integrating one or more aspects selected from the group consisting of: success metrics, benchmarks, and regulations, into the visuals. 
     
     
         12 . A computer system for revising process endpoints by updating strategies based on predicting impacts of exogenous events on original endpoints, the computer system comprising:
 a memory; and   one or more processors in communication with the memory, wherein the computer system is configured to perform a method, said method comprising:
 generating, by the one or more processors, scenarios based on cognitively analyzing external events; 
 cognitively analyzing, by the one or more processors, the process and segmenting the process into components, for each component: 
 determining an endpoint for each component; 
 determining, by the one or more processors, the scenarios relevant to the component; 
 adjusting, by the one or more processors, the endpoint of the component based on the scenarios relevant to the component; 
 applying, by the one or more processors, reinforcement learning to the scenarios relevant to the component to validate impacts of the scenarios on the endpoint and to select a most likely scenario; and 
 implementing, by the one or more processors, process changes to terminate the component at the adjusted endpoint. 
   
     
     
         13 . The computer system of  claim 12 , wherein the components comprise software and hardware engaged in an aspect of the process. 
     
     
         14 . The computer system of  claim 13 , wherein the components comprise components of an enterprise computing system. 
     
     
         15 . The computer system of  claim 12 , wherein cognitively analyzing the process and segmenting the process into the components comprises applying component business model methodology. 
     
     
         16 . The computer system of  claim 12 , wherein generating the scenarios based on cognitively analyzing external events comprises utilizing a large language model to detect trends in the external events and generating the scenarios based on the detected trends. 
     
     
         17 . The computer system of  claim 12 , wherein determining the scenarios relevant to the component comprises applying chain of reasoning factoring to the generated scenarios to determine which of the determined scenarios have greater probabilities of impacting the endpoint. 
     
     
         18 . The computer system of  claim 17 , wherein the scenarios relevant to the component comprise scenarios above a pre-determined probability. 
     
     
         19 . The computer system of  claim 12 , wherein applying the reinforcement learning comprises:
 generating, by the one or more processors, visuals in a user interface of the scenarios relevant to the component; and   obtaining, by the one or more processors, inputs from a user based on the visuals.   
     
     
         20 . A computer program product for revising process endpoints by updating strategies based on predicting impacts of exogenous events on original endpoints, the computer system comprising:
 one or more computer readable storage media and program instructions collectively stored on the one or more computer readable storage media readable by at least one processing circuit to:
 generate scenarios based on cognitively analyzing external events; 
 cognitively analyze the process and segmenting the process into components, for each component: 
 determine an endpoint for each component; 
 determine the scenarios relevant to the component; 
 adjust the endpoint of the component based on the scenarios relevant to the component; 
 apply reinforcement learning to the scenarios relevant to the component to validate impacts of the scenarios on the endpoint and to select a most likely scenario; and 
 implement process changes to terminate the component at the adjusted endpoint.